Xiangyu Zhao

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

GLEAM: Learning to Match and Explain in Cross-View Geo-Localization

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

VisualPRM400K: An Effective Dataset for Training Multimodal Process Reward Models

GenExam: A Multidisciplinary Text-to-Image Exam

MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents

Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning